Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    verbs related to adding or including information

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the continuation or enhancement of a discussion or statement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DragonMagazine
    -0.71
    cffffcc
    -0.68
    cus
    -0.67
     Stronghold
    -0.66
    peg
    -0.65
    visible
    -0.63
    âĻ¦
    -0.63
     Reprodu
    -0.62
    2018
    -0.62
    crow
    -0.61
    POSITIVE LOGITS
    ictions
    0.77
    encies
    0.74
    itri
    0.74
     omin
    0.73
    antly
    0.70
    uations
    0.69
     sarcast
    0.69
    isson
    0.67
    itionally
    0.67
    ensions
    0.66
    Act Density 0.020%

    No Known Activations